Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0353. Min Range: -7.0353
Max Act: 7.0353. Min Act: -0.1700
Data Index: 7231366 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.8165. Min Act: -0.1700
Data Index: 1191473 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.7228. Min Act: -0.1700
Data Index: 5799617 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.6603. Min Act: -0.1700
Data Index: 4673969 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.6915. Min Act: -0.1700
Data Index: 6622070 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.6915. Min Act: -0.1700
Data Index: 8783494 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.6290. Min Act: -0.1700
Data Index: 5752080 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.6603. Min Act: -0.1700
Data Index: 5924046 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.6290. Min Act: -0.1700
Data Index: 8307836 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5978. Min Act: -0.1700
Data Index: 6765659 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5665. Min Act: -0.1700
Data Index: 7922159 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5978. Min Act: -0.1700
Data Index: 7102205 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5978. Min Act: -0.1700
Data Index: 8203187 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5978. Min Act: -0.1700
Data Index: 5607300 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5353. Min Act: -0.1700
Data Index: 1689901 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5665. Min Act: -0.1700
Data Index: 6521756 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5665. Min Act: -0.1700
Data Index: 3520278 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5665. Min Act: -0.1700
Data Index: 8007357 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5665. Min Act: -0.1700
Data Index: 2317513 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0353. Min Range: -7.0353
Max Act: 6.5353. Min Act: -0.1700
Data Index: 5219854 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19